Vibe DESIGN? 🤔 A New First Step To Vibe Coding 🎨 Google Stitch Updates #ai #vibecoding #design
The speaker introduces the concept of 'vibe designing' as a crucial first step before AI coding, arguing that design problems rather than coding problems are the root cause when AI builds something different than intended. They demonstrate how Google Stitch can create interactive previews from multiple screens.
Summary
The video introduces a new concept called 'vibe designing' as a prerequisite to 'vibe coding' with AI. The speaker argues that when AI builds something that doesn't match expectations, the issue typically stems from design problems rather than coding problems. They position vibe designing as the solution to help AI better understand and build what users actually envision. The presentation includes a demonstration of Google Stitch, a tool that can take multiple screens and combine them into an interactive preview that users can navigate through. The speaker promises to cover the key elements of vibe design and explain why this approach should be adopted as a preliminary step in the AI development process.
Key Insights
- The speaker claims that when AI builds something unexpected, it's typically a design problem rather than a coding problem
- The speaker argues that vibe designing should be done before vibe coding to help AI build what users actually imagine
- The speaker demonstrates that Google Stitch can take multiple screens and stitch them together into an interactive preview for navigation
Topics
Transcript
[0:00] If you've ever looked at what your AI built, and you thought, "That's not what I meant." You didn't have a coding problem, you had a design problem. Vibe coding is when you build with AI, but vibe designing is what you should do first. That one change will help AI build what you actually imagine. So, it's going to take all of these screens, and it's going to stitch them together into an interactive preview I can see and move through. Today, I'm going to go through the key elements of vibe design, and why you might want to do that.
Full transcript available for MurmurCast members
Sign Up to AccessMore from Wanderloots
The Future Of AI? 🤯 Hermes Agent Intro & Benefits #ai #agenticai #hermes
Hermes is an AI agent that improves over time by learning from user workflows, unlike most static AI tools. It automatically identifies recurring patterns, creates reusable skills, and applies them to similar future tasks without explicit training.
One Agent, Many Devices? 🧠 Full Hermes Agentic AI + Tailscale Workflow
This tutorial demonstrates how to access a single Hermes AI agent from multiple devices using Tailscale VPN and a remote dashboard setup, enabling unified session history, centralized file access, and continuous memory across laptop and desktop without fragmentation.
Safer Agentic AI? 🧠 Full Docker + Hermes Agent Tutorial (Desktop)
This tutorial demonstrates how to safely run AI agents like Hermes inside Docker containers to sandbox code execution and prevent unauthorized access to sensitive files on your computer. By configuring Docker volumes and mounting specific folders, users can give agents access to only the files they choose while keeping code execution isolated from the main system.
Full Hermes Agent Tutorial (Desktop) 🧠 A Useful Agentic AI Workflow
This tutorial demonstrates how to set up and use Hermes, an open-source AI agent by Nous Research that learns and evolves over time through persistent memory and automated skill generation. The video covers local model setup with Ollama, cloud model integration with OpenAI, messaging gateway configuration via Telegram, and creating a self-improving daily AI briefing automation.
100% Free & Private AI 🦙 Build & Run Local AI Agents #ai #agenticai #ollama #localllm
The video introduces local AI models as a privacy-preserving alternative to cloud-based AI services. By running AI assistants locally on your computer, users can maintain complete control over their data while leveraging AI capabilities for personal tasks like analyzing notes and answering work-related questions.